Re: [OMPI users] [open-mpi/ompi] pmix use of strnlen is not portable (#1771)

Just pushed the fix to master today - not required for 2.x. > On Jun 9, 2016, at 10:44 AM, Siegmar Gross > wrote: > > Hi Ralph, > > Am 08.06.2016 um 21:19 schrieb rhc54: >> Closed #1771 via #1772 >> . >

Re: [OMPI users] [open-mpi/ompi] pmix use of strnlen is not portable (#1771)

Hi Ralph, Am 08.06.2016 um 21:19 schrieb rhc54: Closed #1771 via #1772 . Thank you very much for your help. Now I have new problems with the same program on my Sparc and x86_64 Solaris machines. tyr he

Re: [OMPI users] Processes unable to communicate when using MPI_Comm_spawn on Windows

Gilles: OK, I had assumed MPI_Comm_spawn function was not a big stretch of the other basic capabilities. The openmpi windows pre-compiled library was obtained from this very website: https://www.open-mpi.org/software/ompi/v1.6/downloads/OpenMPI_v1.6.2-2_win64.exe Windows support was ended near

Re: [OMPI users] Processes unable to communicate when using MPI_Comm_spawn on Windows

Jeff: Thanks for the extremely informative reply! I can appreciate the reasons for dropping of Windows support. The reason for wanting a Windows version of this scientific calculation software is to allow the non-programmerish end-users be able to run it 'out of the box' using precompiled Wind

Re: [OMPI users] Processes unable to communicate when using MPI_Comm_spawn on Windows

Christopher, just to be clear, MPI_Comm_spawn is *not* a basic functionality. also, it might work on older windows (xp for example) you might want to report thus issue to whoever provided this Open MPI pre-compiled library. an other option is to use cygwin, it provides a fairly recent Open MPI an

Re: [OMPI users] Processes unable to communicate when using MPI_Comm_spawn on Windows

I think there were a few not-entirely-correct data points in this thread. Let me clarify a few things: 1. Yes, Open MPI suspended native Windows support a while back. Native windows support is simply not a popular use case, and therefore we couldn't justify spending the time on it (not the me

Re: [OMPI users] Processes unable to communicate when using MPI_Comm_spawn on Windows

Thanks for the info, Gilles. Being relatively new to MPI, I was not aware 'sm' did not work with intercommunicators - I had assumed it was an option if the others were not available. I am running as an admin on this test machine. When adding the option '-mca btl_tcp_port_min_v4 2000', a higher

Re: [OMPI users] . cuda-memcheck reports errors for MPI functions after use of cudaSetDevice

Hi Jiri, thank you for your reply. That is a good thing to know, I will ignore those error messages then. Best regards, Kristina > Am 09.06.2016 um 09:13 schrieb Jiri Kraus : > > Hi Kristina, > > Although its reported by cuda-memcheck as an error it really is an expected > return code from

Re: [OMPI users] . cuda-memcheck reports errors for MPI functions after use of cudaSetDevice

Hi Kristina, Although its reported by cuda-memcheck as an error it really is an expected return code from cuPointerGetAttributes. The CUDA-aware build of OpenMPI calls cuPointerGetAttributes to query if a pointer is a host or device pointer. Memory allocated with the system allocator (malloc, g